Generative AI enables scalable production of educational videos, but current systems largely focus on producing visually coherent content rather than supporting learning. As a result, generated videos often lack explicit pedagogical structure, reliable quality control, and mechanisms for assessing learner understanding...
Xinchen Ma, Shuimu Wang, Gaole He et al.· 0 citations
SPS is a training-free latent steering framework that constructs a state-conditioned Direction Bank containing multiple progress-guided steering vectors for different prefix-state regions and applies it at high-uncertainty transitions to guide the next reasoning step toward meaningful progress.
Hengyuan Zhang, Chenming Shang, Zun-Hai Su et al.· 0 citations
This paper formulates narrative coding as gated, typed decisions answered by Jev, a System One model that returns probabilities over analyst-defined options and generates no text.
Generating coherent meta-reviews from multiple peer reviews is challenging when reviewer evidence conflicts and varies in reliability. Existing approaches typically formulate meta-review generation as a multi-document summarization task and aggregate reviewer feedback uniformly, making it difficult to determine which o...
Xin-Zhe Wang, Fei Tao, Jiang Xie et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces STAT-TO-TEXT, a controlled task in which LLMs generate quantified natural language inferences from statistical tables using quantified constructions such as all, some, no, and most, and uses an LLM generated Python checker code to evaluate these inferences.
Mai Mohamed Eida, Gunjan Anand, Ashutosh Kumar Singh et al.· 0 citations
An open implementation of JevLite of this readout, JevLite, on scam-call screening, with a fine-tuned ModernBERT encoder and an evaluation reporting calibration, false alarms and decision timing alongside AUROC.
Previous work on Egyptian Arabic in NLP has focused largely on the prestigious Cairene Egyptian Arabic (CEA) dialect, resulting in a lack of representation for the less prestigious Sa'idi Egyptian Arabic (SEA) dialect both in LLM and resource development. Does this lack of representation influence an LLM's view of the...
Mai Mohamed Eida, Ryan Dolan, Paul Leonce Irma De Nijs et al.· 0 citations
Expressive speech synthesis has advanced through prosody modeling, yet generating structured poetic speech, such as haiku, remains challenging. Prior work on prosody transfer improves expressiveness, and fine-tuned poetry TTS (text-to-speech) systems capture verse intonation. However, these models do not model haiku's...
Devangi Sharma, Sophia Judicke, Glenda Tan et al.· 0 citations
Effective communication between users and AI agents is essential for human-AI collaboration. The XY problem is a well-known communication pitfall where a person asks about their attempted solution rather than their actual problem. We extend prior sycophancy evaluation to the XY problem in agentic settings, evaluating w...
Zheng-Xuan Wu, Yuxuan Li, O. Tafjord et al.· 0 citations
Post-training turns a general next-token predictor into a chat model with a persistent assistant persona. If that persona is a character the model plays only on its own turns, its preferences should govern what the assistant says, not what the model predicts other speakers will say. We test this boundary and find that...
This work evaluates continued pretraining on FineWeb-Edu dumps drawn strictly from after each model's knowledge cutoff, evaluated across six open-weight models spanning three families and four parameter scales, painting a more optimistic picture of time-incremental CPT than the prior continual learning literature sugge...
Firat Öncel, S. Ali, M. Ravanelli et al.· 0 citations
Software delegates more of its branches to models every year: which queue a ticket enters, whether a command is safe to run, whether a claim clears without a person. What the program needs back is not prose. It is one of n declared options and a number it can threshold. Today that costs a round trip to a frontier model...
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
